cavuno-board-seo

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill instructions involve ingesting data from external API sources (job listings, blog posts, salary details) to generate JSON-LD structured data, creating an indirect prompt injection surface.
  • Ingestion points: Data is retrieved from the board object using methods like board.jobs.retrieve, board.blog.posts.retrieve, and board.salaries.titles.retrieve across JOB_AND_BREADCRUMBS.md, BLOG.md, and SALARY.md.
  • Boundary markers: The provided implementation snippets do not include explicit boundary markers or "ignore embedded instructions" warnings when processing these external data objects.
  • Capability inventory: The skill is designed to generate content for application/ld+json script tags and HTML head metadata (title, description, Open Graph tags).
  • Sanitization: The skill relies on the @cavuno/board/seo SDK builders to correctly serialize and sanitize external data before it is emitted into the page's HTML context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:07 AM
Security Audit — agent-trust-hub — cavuno-board-seo